GR

granite3 instruct 8b

GraniteGGUF by trufaeUpdated 2024-10-22
Download on Hugging Face
Parameters8.17B
Context4K
Layers40
Architecturegranite
Smallest quant2.5 GB
Quick answer

granite3 instruct 8b needs about 6.4 GB of memory at its main file (a 4.6 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 4 quants, from 2.5 GB to 8.7 GB.

granite3 instruct 8b is a 8.17B-parameter Granite model in GGUF format, quantized by trufae. Its trained context length is 4K tokens. The repository has 4 quant files, from 2.5 GB to 8.7 GB.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—2.5 GB 3.6 GB
Fits Get file →
—4.6 GB 5.8 GB
Fits Get file →
—5.1 GB 6.3 GB
Fits Get file →
—8.7 GB 9.9 GB
Too big Get file →

What GPU do you need for granite3 instruct 8b?

These figures add the file size, an fp16 KV cache at an 8K context window (worked out from this model’s own header) and about 0.5 GB for the runtime. They are estimates, so leave a little headroom, and expect to use less context or a smaller quant if you are right at the limit.

  • 4 GB VRAM: no quant fits at an 8K context.
  • 6 GB VRAM: the best quant that fits is the main file (2.5 GB file, about 4.3 GB in use).
  • 8 GB VRAM: the best quant that fits is the main file (5.1 GB file, about 7.0 GB in use).
  • 12 GB VRAM: the best quant that fits is the main file (8.7 GB file, about 10.5 GB in use).

Which granite3 instruct 8b quant should you choose?

If memory is tight, the smallest file is the first one in the table at 2.5 GB, with the quality trade-offs that come with fewer bits.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturegranite
Parameters8.17B
Layers40
Trained context4,096 tokens
KV cache (fp16)160 KB per token

Source

Quantized bytrufae
FamilyGranite
Licenseapache-2.0
Downloads (HF)14
Last updated2024-10-22

Frequently asked questions about granite3 instruct 8b

How much VRAM does granite3 instruct 8b need?

About 6.4 GB at its main file with an 8K context window. That is the 4.6 GB file, plus the KV cache and roughly 0.5 GB of runtime overhead. Smaller quants need less and longer context needs more.

Can I run granite3 instruct 8b on an 8 GB GPU?

Yes, with the smaller files: the 5.1 GB file needs about 7.0 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of granite3 instruct 8b GGUF?

It depends on the quant: file is 2.5 GB, file is 4.6 GB, file is 5.1 GB, file is 8.7 GB.

What context length does granite3 instruct 8b support?

The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 1.3 GB at 8K and 0.7 GB at 4K.

Where can I download granite3 instruct 8b GGUF?

The files are on Hugging Face in the trufae/granite3-instruct-8b-gguf repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does granite3 instruct 8b use?

Hugging Face lists the license as apache-2.0. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.

Similar models

Browse all →

More from trufae

All by trufae →

More Granite models

All Granite →

Other small models

All small models →